© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19643
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    np_acts-logits-general · gemini-2.5-flash-lite

    geographical locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     între
    0.42
     सर्वप्रथम
    0.41
     skall
    0.40
     Wheeler
    0.36
     रिट
    0.36
     partitions
    0.35
     л
    0.35
     하여
    0.35
     Goldstein
    0.34
     न्याय
    0.34
    POSITIVE LOGITS
     Kuala
    0.39
     Dhaka
    0.39
     দূতাবাসের
    0.37
    Nepal
    0.37
    akarta
    0.37
    usalem
    0.37
    ্কৃত
    0.36
    Asie
    0.36
     Chọn
    0.36
    stanbul
    0.35
    Activations Density 0.035%

    No Known Activations